Skip to main content
GET
Error

Authorizations

​
X-API-Key
string
header
required

Query Parameters

​
offset
integer
default:0

Number of entries to skip before this page.

Required range: x >= 0
​
limit
integer
default:100

Maximum number of entries to return.

Required range: 1 <= x <= 100
​
q
string | null

Case-insensitive substring matched against the entry name, match pattern, and provider. Hyphens and spaces are treated as equivalent.

Maximum string length: 200
​
provider
string[] | null

Only return price maps for these providers (case-insensitive).

Maximum array length: 20
Minimum string length: 1
​
sort_by
string | null

Field to sort on. Defaults to match priority order.

Allowed value: "start_time"
​
sort_order
enum<string>
default:desc

Sort direction for sort_by. Unset start dates sort last.

Available options:
asc,
desc

Response

Successful Response

​
name
string
required

Display name for the entry, usually the model name.

​
match_pattern
string
required

Regular expression matched against the run's model name, for example ^gpt-4o-mini$.

​
prompt_cost
string
required

Cost in US dollars per input (prompt) token.

Pattern: ^(?!^[-+.]*$)[+-]?0*\d*\.?\d*$
​
completion_cost
string
required

Cost in US dollars per output (completion) token.

Pattern: ^(?!^[-+.]*$)[+-]?0*\d*\.?\d*$
​
id
string<uuid>

ID of the entry.

​
start_time
string<date-time> | null

Only price runs that started at or after this time. Null applies to runs from any time.

​
tenant_id
string<uuid> | null

Workspace that owns the entry. Null for LangSmith default entries, which cannot be updated or deleted.

​
match_path
string[]

Invocation parameter keys checked, in order, for the model name when the run does not report ls_model_name metadata.

​
prompt_cost_details
Prompt Cost Details · object | null

Cost in US dollars per input token for specific token types, keyed by the token detail name the run reports, for example cache_read. Input tokens not covered here are priced at prompt_cost.

​
completion_cost_details
Completion Cost Details · object | null

Cost in US dollars per output token for specific token types, keyed by the token detail name the run reports, for example audio. Output tokens not covered here are priced at completion_cost.

​
provider
string | null

Only price runs from this provider (the ls_provider metadata, case-insensitive), for example openai or anthropic. Null matches any provider.

​
prompt_tokens_above
integer | null

Only price requests with more input tokens than this, for long-context pricing tiers. Null applies to every request.

Required range: 0 <= x <= 9007199254740991